© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8849
    Prev
    Next
    INDEX
    Explanations

    text in Portuguese related to coding and streams

    oai_token-act-pair · gemini-2.0-flash

    Portuguese language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.69
    rungsseite
    -0.64
     تضيفلها
    -0.60
     переписи
    -0.60
    OGND
    -0.59
    mybatisplus
    -0.57
    تقاوى
    -0.56
     mas
    -0.56
    TypedDataSet
    -0.56
     estekak
    -0.55
    POSITIVE LOGITS
    /*
    0.57
    InjectAttribute
    0.51
    strij
    0.50
    uteen
    0.49
     ویکی‌پدیای
    0.48
    URIComponent
    0.48
     ToString
    0.47
    cookieParser
    0.47
     hâte
    0.46
     consultato
    0.46
    Activations Density 0.357%

    No Known Activations